Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model

The cryptocurrency market has been developed at an unprecedented speed over the past few years. Cryptocurrency works similar to standard currency, however, virtual payments are made for goods and services without the intervention of any central authority. Although cryptocurrency ensures legitimate a...

Full description

Saved in:
Bibliographic Details
Main Authors: Naila Aslam, Furqan Rustam, Ernesto Lee, Patrick Bernard Washington, Imran Ashraf
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9751065/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209369839370240
author Naila Aslam
Furqan Rustam
Ernesto Lee
Patrick Bernard Washington
Imran Ashraf
author_facet Naila Aslam
Furqan Rustam
Ernesto Lee
Patrick Bernard Washington
Imran Ashraf
author_sort Naila Aslam
collection DOAJ
description The cryptocurrency market has been developed at an unprecedented speed over the past few years. Cryptocurrency works similar to standard currency, however, virtual payments are made for goods and services without the intervention of any central authority. Although cryptocurrency ensures legitimate and unique transactions by utilizing cryptographic methods, this industry is still in its inception and serious concerns have been raised about its use. Analysis of the sentiments about cryptocurrency is highly desirable to provide a holistic view of peoples’ perceptions. In this regard, this study performs both sentiment analysis and emotion detection using the tweets related to the cryptocurrency which are widely used for predicting the market prices of cryptocurrency. For increasing the efficacy of the analysis, a deep learning ensemble model LSTM-GRU is proposed that combines two recurrent neural networks applications including long short term memory (LSTM) and gated recurrent unit (GRU). LSTM and GRU are stacked where the GRU is trained on the features extracted by LSTM. Utilizing term frequency-inverse document frequency, word2vec, and bag of words (BoW) features, several machine learning and deep learning approaches and a proposed ensemble model are investigated. Furthermore, TextBlob and Text2Emotion are studied for emotion analysis with the selected models. Comparatively, a larger number of people feel happy with the use of cryptocurrency, followed by fear and surprise emotions. Results suggest that the performance of machine learning models is comparatively better when BoW features are used. The proposed LSTM-GRU ensemble shows an accuracy of 0.99 for sentiment analysis, and 0.92 for emotion prediction and outperforms both machine learning and state-of-the-art models.
format Article
id doaj-art-accef814ed23471eb7fea8138aedda44
institution OA Journals
issn 2169-3536
language English
publishDate 2022-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-accef814ed23471eb7fea8138aedda442025-08-20T02:10:01ZengIEEEIEEE Access2169-35362022-01-0110393133932410.1109/ACCESS.2022.31656219751065Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU ModelNaila Aslam0Furqan Rustam1https://orcid.org/0000-0001-8403-1047Ernesto Lee2https://orcid.org/0000-0002-1209-8565Patrick Bernard Washington3https://orcid.org/0000-0002-3596-9167Imran Ashraf4https://orcid.org/0000-0002-8271-6496School of Electronics and Information Engineering, Hebei University of Technology, Tianjin, ChinaDepartment of Software Engineering, School of Systems and Technology, University of Management and Technology, Lahore, PakistanDepartment of Computer Science, Broward College, Broward County, Fort Lauderdale, FL, USADivision of Business Administration and Economics, Morehouse College, Atlanta, GA, USADepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, South KoreaThe cryptocurrency market has been developed at an unprecedented speed over the past few years. Cryptocurrency works similar to standard currency, however, virtual payments are made for goods and services without the intervention of any central authority. Although cryptocurrency ensures legitimate and unique transactions by utilizing cryptographic methods, this industry is still in its inception and serious concerns have been raised about its use. Analysis of the sentiments about cryptocurrency is highly desirable to provide a holistic view of peoples’ perceptions. In this regard, this study performs both sentiment analysis and emotion detection using the tweets related to the cryptocurrency which are widely used for predicting the market prices of cryptocurrency. For increasing the efficacy of the analysis, a deep learning ensemble model LSTM-GRU is proposed that combines two recurrent neural networks applications including long short term memory (LSTM) and gated recurrent unit (GRU). LSTM and GRU are stacked where the GRU is trained on the features extracted by LSTM. Utilizing term frequency-inverse document frequency, word2vec, and bag of words (BoW) features, several machine learning and deep learning approaches and a proposed ensemble model are investigated. Furthermore, TextBlob and Text2Emotion are studied for emotion analysis with the selected models. Comparatively, a larger number of people feel happy with the use of cryptocurrency, followed by fear and surprise emotions. Results suggest that the performance of machine learning models is comparatively better when BoW features are used. The proposed LSTM-GRU ensemble shows an accuracy of 0.99 for sentiment analysis, and 0.92 for emotion prediction and outperforms both machine learning and state-of-the-art models.https://ieeexplore.ieee.org/document/9751065/Cryptocurrencysentiment analysisText2Emotionemotion analysismachine learning
spellingShingle Naila Aslam
Furqan Rustam
Ernesto Lee
Patrick Bernard Washington
Imran Ashraf
Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model
IEEE Access
Cryptocurrency
sentiment analysis
Text2Emotion
emotion analysis
machine learning
title Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model
title_full Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model
title_fullStr Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model
title_full_unstemmed Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model
title_short Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model
title_sort sentiment analysis and emotion detection on cryptocurrency related tweets using ensemble lstm gru model
topic Cryptocurrency
sentiment analysis
Text2Emotion
emotion analysis
machine learning
url https://ieeexplore.ieee.org/document/9751065/
work_keys_str_mv AT nailaaslam sentimentanalysisandemotiondetectiononcryptocurrencyrelatedtweetsusingensemblelstmgrumodel
AT furqanrustam sentimentanalysisandemotiondetectiononcryptocurrencyrelatedtweetsusingensemblelstmgrumodel
AT ernestolee sentimentanalysisandemotiondetectiononcryptocurrencyrelatedtweetsusingensemblelstmgrumodel
AT patrickbernardwashington sentimentanalysisandemotiondetectiononcryptocurrencyrelatedtweetsusingensemblelstmgrumodel
AT imranashraf sentimentanalysisandemotiondetectiononcryptocurrencyrelatedtweetsusingensemblelstmgrumodel